Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slack
    -0.07
     hurd
    -0.06
    _UNIX
    -0.06
    ичес
    -0.06
    ad
    -0.06
     forehead
    -0.06
     Marvel
    -0.06
    陸
    -0.06
    advert
    -0.06
    >true
    -0.06
    POSITIVE LOGITS
    :"-
    0.06
     swear
    0.06
     slowdown
    0.06
    generic
    0.06
    =q
    0.06
     ČR
    0.06
     caf
    0.06
     alcan
    0.06
     созд
    0.06
     klim
    0.06
    Act Density 0.000%

    No Known Activations